| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.32142857142857145, | |
| "eval_steps": 500, | |
| "global_step": 18, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08928571428571429, | |
| "grad_norm": 0.3432307541370392, | |
| "learning_rate": 4.9997541293989384e-05, | |
| "loss": 1.5088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 0.3968185484409332, | |
| "learning_rate": 4.999016565957633e-05, | |
| "loss": 1.5959, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 0.2845610976219177, | |
| "learning_rate": 4.9977874547522175e-05, | |
| "loss": 1.3605, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1672029526818816.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |